Automatic Detection of Putative Mild Cognitive Impairment from Speech Acoustic Features in Mandarin-Speaking Elders

Article type: Research Article

Authors: Wang, Rumi^a | Kuang, Chen^b | Guo, Chengyu^b | Chen, Yong^c | Li, Canyang^a | Matsumura, Yoshihiro^d | Ishimaru, Masashi^d | Van Pelt, Alice J.^{e; f} | Chen, Fei^{b; *}

Affiliations: [a] Rehabilitation Medicine Department, Speech and Language Pathology Therapy Section, The Second Xiangya Hospital of Central South University, Changsha, Hunan, China | [b] School of Foreign Languages, Hunan University, Hunan, China | [c] Laboratory of Food Oral Processing, School of Food Science & Biotechnology, Zhejiang Gongshang University, Hangzhou, Zhejiang, China | [d] Panasonic Electric Works Co., Ltd, Osaka, Japan | [e] Section of Gastroenterology, Edward Hines, Jr. VA Hospital, Hines, IL, USA | [f] Division of Gastroenterology and Nutrition, Loyola University Stritch School of Medicine, Maywood, IL, USA

Correspondence: [*] Correspondence to: Fei Chen, School of Foreign Languages, Hunan University, Lushannan Road No. 2, Yuelu District, Changsha City, Hunan Province, China. E-mail: [email protected].

Abstract: Background:To date, the reliable detection of mild cognitive impairment (MCI) remains a significant challenge for clinicians. Very few studies investigated the sensitivity of acoustic features in detecting Mandarin-speaking elders at risk for MCI, defined as “putative MCI” (pMCI). Objective:This study sought to investigate the possibility of using automatically extracted speech acoustic features to detect elderly people with pMCI and reveal the potential acoustic markers of cognitive decline at an early stage. Methods:Forty-one older adults with pMCI and 41 healthy elderly controls completed four reading tasks (syllable utterance, tongue twister, diadochokinesis, and short sentence reading), from which acoustic features were extracted automatically to train machine learning classifiers. Correlation analysis was employed to evaluate the relationship between classifier predictions and participants’ cognitive ability measured by Mini-Mental State Examination 2. Results:Classification results revealed that some temporal features (e.g., speech rate, utterance duration, and the number of silent pauses), spectral features (e.g., variability of F1 and F2), and energy features (e.g., SD of peak intensity and SD of intensity range) were effective predictors of pMCI. The best classification result was achieved in the Random Forest classifier (accuracy = 0.81, AUC = 0.81). Correlation analysis uncovered a strong negative correlation between participants’ cognitive test scores and the probability estimates of pMCI in the Random Forest classifier, and a modest negative correlation in the Support Vector Machine classifier. Conclusions:The automatic acoustic analysis of speech could provide a promising non-invasive way to assess and monitor the early cognitive decline in Mandarin-speaking elders.

Keywords: Alzheimer’s disease, machine learning, Mandarin, mild cognitive impairment, speech

DOI: 10.3233/JAD-230373

Journal: Journal of Alzheimer's Disease, vol. 95, no. 3, pp. 901-914, 2023